Curriculum Vitae

Curriculum Vitae

Person-Related Identification Information

• RNDr. Vít Novotný, Ph.D., born on October 6, 1992 in Český Krumlov, Czechia.

Department

• Faculty of Informatics, Masaryk University (FI MU)
  Department of Machine Learning and Data Processing
  Botanická 68a, 602 00 Brno, Czechia
  e-mail: witiko@mail.muni.cz, witiko@gmail.com

Employment - Position

• Research Scientist, Course Instructor, Thesis Supervisor

Education and Academic Qualifications

• 2022: Doctoral, Fundamentals of Computer Science, Ph.D., Doctoral Thesis “Interpretable Representations for Fast and Accurate Retrieval of Mathematical Information”, FI MU (recording of thesis defense)
• 2020: Doctoral, Computer Systems, Communications, and Security, RNDr., Rigorous Thesis “Document Representations for Fast and Accurate Retrieval of Mathematical Information”, FI MU (recording of state doctoral exam)
• 2018: Graduate, Applied Computer Science, Mgr., Master's Thesis “Vector Space Representations in Information Retrieval”, FI MU
• 2015: Undergraduate, Applied Computer Science, Bc., Bachelor's Thesis “The Form of Theses Written in LaTeX”, FI MU
• 2012: High school, -, Cambridge C2 Proficiency (CPE), -, Bishop's Gymnasium of Saint John Neumann in České Budějovice (Czechia)

Employment

• 2017–2021: Development of the Digital Library Catalogue of the Masaryk University, ÚVT MU
• 2015–now: Development of LaTeX templates, FI MU

Teaching Activities

• 2018–now: Introduction to Information Retrieval (FI MU, graduate)
• 2015–now: Electronic Document Preparation (FI MU, undergraduate)

Scientific and Research Activities

• 2020–2023: Research of Optical Character Recognition (OCR), Information Retrieval (IR), and Named Entity Recognition (NER) for grant project “Accessible historical sources (AHISTO). Making medieval written documents available in the form of a contextual database”
• , TACR 2016–2017: Research of Similarity Search for grant project “Intelligent software for semantic text search (ISSHD)”, TACR

Activities Outside University

• 2022: Organisation of the Answer Retrieval for Questions on Math (ARQMath-3) lab at CLEF 2022
• 2019: Organisation of the Czech Premiere of Donald Knuth's oratorio “Fantasia Apocalyptica” and audiovisual editing of its recording
• 2018–now: Development of the Free Open-Source Gensim Package (Python, Cython)
• 2016–now: Development of the Free Open-Source Markdown Package (TeX, Lua)
• 2016–now: Board member of the Czechoslovak TeX Users Group (CSTUG) and assistant editor-in-chief of the CSTUG Bulletin
• 2008–now: Music production at personal YouTube channel

Awards Related to Science and Research

• 2018: Brno Ph.D. Talent from the South Moravian Centre for International Mobility (JCMM)
• 2017: Dean's Award for an Outstanding Master's Thesis “Vector Space Representations in Information Retrieval” from FI MU
• 2016: Praise for student R&D project “A Markdown Interpreter in TeX” from FI MU
• 2015: Praise for student R&D project “ISO 690:2011 Bibliography Style for BibLaTeX” from FI MU
• 2015: Dean's Award for an Outstanding Bachelor' Thesis “The Form of Theses Written in LaTeX” from FI MU
• 2015: Praise for student R&D project “The Fithesis3 LaTeX Template for Writing Theses” from FI MU

Major Publications

• NOVOTNÝ, Vít, Kristýna LUGER, Michal ŠTEFÁNIK, Tereza VRABCOVÁ and Aleš HORÁK. People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts. Online. In Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki. Findings of the Association for Computational Linguistics: ACL 2023. Toronto, Canada: Association for Computational Linguistics, 2023, p. 14104-14113. ISBN 978-1-959429-62-3. article preprint info
• STARÝ NOVOTNÝ, Vít. Markdown 3: What's new, what's next? In TUG 2023. 2023. video recording presentation slides info
• NOVOTNÝ, Vít, Michal ŠTEFÁNIK, Eniafe Festus AYETIRAN, Petr SOJKA and Radim ŘEHŮŘEK. When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting. Journal of Universal Computer Science. New York, USA: J.UCS Consortium, 2022, vol. 28, No 2, p. 181-201. ISSN 0948-695X. Available from: https://dx.doi.org/10.3897/jucs.69619. preprint DOI info
• ŠTEFÁNIK, Michal, Vít NOVOTNÝ, Nikola GROVEROVÁ and Petr SOJKA. AdaptOr: Objective-Centric Adaptation Framework for Language Models. Online. In Valerio Basile, Zornitsa Kozareva, Sanja Stajner. Proceedings of the 60th Conference of Association of Computational Linguistics, ACL 2022. Dublin, Irsko: Association for Computational Linguistics, ACL, 2022, p. 261-269. ISBN 978-1-955917-24-7. Available from: https://dx.doi.org/10.18653/v1/2022.acl-demo.26. paper with code Preprint publisher's PDF info
• MANSOURI, Behrooz, Vít NOVOTNÝ, Anurag AGARWAL, Douglas W. OARD and Richard ZANIBBI. Overview of ARQMath-3 (2022): Third CLEF Lab on Answer Retrieval for Questions on Math (Working Notes Version). Online. In Guglielmo Faggioli, Nicola Ferro, Allan Hanbury, Martin Potthast. Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum. Bologna: CEUR-WS, 2022, p. 1-27. ISSN 1613-0073. fulltext PDF info
• AYETIRAN, Eniafe Festus, Petr SOJKA and Vít NOVOTNÝ. EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses. Knowledge-Based Systems. Elsevier, 2021, vol. 2021, No 219, p. 106902-106915. ISSN 0950-7051. Available from: https://dx.doi.org/10.1016/j.knosys.2021.106902. DOI preprint info
• NOVOTNÝ, Vít. Interpretable Document Representations for Fast and Accurate Retrieval of Mathematical Information. Online. In SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2021, p. 2705-2705. ISBN 978-1-4503-3621-5. Available from: https://dx.doi.org/10.1145/3404835.3463269. conference web DOI info
• NOVOTNÝ, Vít, Eniafe Festus AYETIRAN, Dalibor BAČOVSKÝ, Dávid LUPTÁK, Michal ŠTEFÁNIK and Petr SOJKA. One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages. In Mitkov, Ruslan and Angelova, Galia. Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021). Varna, Bulgaria: INCOMA Ltd., 2021, p. 1068-1074. ISBN 978-954-452-072-4. Available from: https://dx.doi.org/10.26615/978-954-452-072-4_120. DOI preprint sborníku preprint info
• ŠTEFÁNIK, Michal, Vít NOVOTNÝ and Petr SOJKA. Regressive Ensemble for Machine Translation Quality Evaluation. Online. In Loïc Barrault et al. Proceedings of EMNLP 2021 Sixth Conference on Machine Translation (WMT 21). Online and Punta Cana, Dominican Republi: ACL, 2021, p. 1041-1048. ISBN 978-1-954085-94-7. paper preprint info
• SOJKA, Petr, Michal RŮŽIČKA and Vít NOVOTNÝ. MIaS: Math-Aware Retrieval in Digital Mathematical Libraries. Online. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM '18). Torino, Italy: Association for Computing Machinery, 2018, p. 1923-1926. ISBN 978-1-4503-6014-2. Available from: https://dx.doi.org/10.1145/3269206.3269233. DOI Postprint info
• NOVOTNÝ, Vít. Implementation Notes for the Soft Cosine Measure. Online. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM '18). Torino, Italy: Association for Computing Machinery, 2018, p. 1639-1642. ISBN 978-1-4503-6014-2. Available from: https://dx.doi.org/10.1145/3269206.3269317. Postprint DOI info
• RYGL, Jan, Jan POMIKÁLEK, Radim ŘEHŮŘEK, Michal RŮŽIČKA, Vít NOVOTNÝ and Petr SOJKA. Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines. Online. In Proceedings of the 2nd Workshop on Representation Learning for NLP, RepL4NLP 2017 c/o ACL 2017. Vancouver, Canada: Association for Computational Linguistics, ACL, 2017, p. 81-90. ISBN 978-1-945626-62-3. Available from: https://dx.doi.org/10.18653/v1/W17-2611. Preprint Article info

2023/01/03

Another Variant: Czech(1)